Sarvam AI is releasing Sarvam 30B and Sarvam 105B as open-source models, trained from scratch on large-scale, high-quality datasets. These models demonstrate strong reasoning, programming, and agentic capabilities, with optimizations for efficient deployment across various hardware. Sarvam 30B powers Samvaad, while Sarvam 105B powers Indus. The release includes details on the model architecture, training process, benchmark results, and inference optimizations. The models are available on AI Kosh and Hugging Face, and the article details their performance across benchmarks and in real-world applications like webpage generation, JEE problem solving, and conversational agents.
Júlio Falbo argues that integrating AI into engineering organizations is hampered by complex connection methods, proposing a solution centered around “SKILL.md” – Markdown files defining tool usage – and “AI Gateways” for centralized orchestration. This combination fosters an “AI-native architecture” prioritizing ease of use, governance, and scalability over bespoke integrations. Ultimately, this approach shifts the focus from complex coding to clear documentation, democratizing AI tool access and boosting productivity.
* Simplifies AI integration via Markdown-based "skills."
* Utilizes AI Gateways for centralized control and security.
* Promotes a convention-over-configuration approach for AI systems.
* Simplifies AI integration via Markdown-based "skills."
* Utilizes AI Gateways for centralized control and security.
* Promotes a convention-over-configuration approach for AI systems.
Developers are replacing bloated MCP servers with Markdown skill files — cutting token costs by 100x. This article explores a two-layer architecture emerging in production AI systems, separating knowledge from execution. It details how skills (Markdown files) encode stable knowledge, while MCP servers handle runtime API interactions. The piece advocates for a layered approach to optimize context window usage, reduce costs, and improve agent reasoning by prioritizing knowledge representation in a version-controlled, accessible format.
MIT researchers developed a new approach that rethinks how a classic method, known as Bayesian optimization, can be used to solve problems with hundreds of variables. In tests on realistic engineering-style benchmarks, like power-system optimization, the approach found top solutions 10 to 100 times faster than widely used methods.
Their technique leverages a foundation model trained on tabular data that automatically identifies the variables that matter most for improving performance, repeating the process to hone in on better and better solutions. The researchers’ tabular foundation model does not need to be constantly retrained as it works toward a solution, increasing the efficiency of the optimization process.
The technique also delivers greater speedups for more complicated problems, so it could be especially useful in demanding applications like materials development or drug discovery. The research will be presented at the International Conference on Learning Representations.
Their technique leverages a foundation model trained on tabular data that automatically identifies the variables that matter most for improving performance, repeating the process to hone in on better and better solutions. The researchers’ tabular foundation model does not need to be constantly retrained as it works toward a solution, increasing the efficiency of the optimization process.
The technique also delivers greater speedups for more complicated problems, so it could be especially useful in demanding applications like materials development or drug discovery. The research will be presented at the International Conference on Learning Representations.
This article details how to use Ollama to run large language models locally, protecting sensitive data by keeping it on your machine. It covers installation, usage with Python, LangChain, and LangGraph, and provides a practical example with FinanceGPT, while also discussing the tradeoffs of using local LLMs.
PycoClaw brings full OpenClaw agent parity to embedded hardware — a MicroPython-powered AI agent that can run on a $5 microcontroller. It features one-click flashing, a full agent loop, hardware control, multi-channel chat, persistent memory, and ScriptOs skills.
PycoClaw is an open-source platform for running AI agents on microcontrollers. It brings OpenClaw workspace-compatible intelligence to embedded devices costing under $5. Built on MicroPython, it supports multi-provider LLM routing, multi-channel chat, tool calling, extensions, over-the-air updates, and battery operation.
Adafruit highlights the development of “pycoClaw,” a fully-featured AI agent implemented in MicroPython and running on a $5 ESP32-S3. This agent boasts capabilities like recursive tool calling, persistent memory using SD card storage, and a touchscreen UI, all built with an async architecture and optimized for performance through C user modules. The project is open-source and supports various hardware platforms, with ongoing development for RP2350, and is showcased alongside other Adafruit news including new product releases, community events, and resources for makers.
Agent Skills are a simple, open format for giving agents new capabilities and expertise. They are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently.
yoagent is a simple, effective agent loop with tool execution and event streaming in Rust. Inspired by pi-agent-core. It features a stateful agent, multi-provider support, built-in tools, and context management.
